English
Related papers

Related papers: Mining or Synthesis? Rethinking Exploration Effici…

200 papers

Direct Preference Optimization (DPO) is a method for enhancing model performance by directly optimizing for the preferences or rankings of outcomes, instead of traditional loss functions. This approach has proven effective in aligning Large…

Machine Learning · Computer Science 2024-09-18 Ruoyu Wang , Jiachen Sun , Shaowei Hua , Quan Fang

Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence regularization that creates an inherent dilemma: strong…

Machine Learning · Computer Science 2025-10-22 Jiajun Fan , Tong Wei , Chaoran Cheng , Yuxin Chen , Ge Liu

We introduce ConfPO, a method for preference learning in Large Language Models (LLMs) that identifies and optimizes preference-critical tokens based solely on the training policy's confidence, without requiring any auxiliary models or…

Computation and Language · Computer Science 2025-06-13 Hee Suk Yoon , Eunseop Yoon , Mark Hasegawa-Johnson , Sungwoong Kim , Chang D. Yoo

When a large language model under reinforcement learning commits a wrong reasoning step early in a trajectory, standard algorithms force it to keep generating until the maximum horizon, spending compute on tokens that never receive positive…

Machine Learning · Computer Science 2026-05-29 Zihang Li , Rui Zhou , Yingcheng Shi , Wenhan Yu , Zhewen Tan , Zixiang Liu , Zeming Li , Binhua Li , Yongbin Li , Tong Yang , Jieping Ye

The rapid rise of large language models (LLMs) has unlocked many applications but also underscores the challenge of aligning them with diverse values and preferences. Direct Preference Optimization (DPO) is central to alignment but…

Diffusion models have achieved remarkable progress in text-to-image generation, yet aligning them with human preference remains challenging due to the presence of multiple, sometimes conflicting, evaluation metrics (e.g., semantic…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Dipesh Tamboli , Souradip Chakraborty , Aditya Malusare , Biplab Banerjee , Amrit Singh Bedi , Vaneet Aggarwal

Large Language Models (LLMs) can become outdated over time as they may lack updated world knowledge, leading to factual knowledge errors and gaps. Knowledge Editing (KE) aims to overcome this challenge using weight updates that do not…

Computation and Language · Computer Science 2024-09-25 Amit Rozner , Barak Battash , Lior Wolf , Ofir Lindenbaum

Online on-policy preference learning algorithms for language model alignment such as online direct policy optimization (DPO) can significantly outperform their offline counterparts. We provide a theoretical explanation for this phenomenon…

Machine Learning · Computer Science 2026-01-14 Juno Kim , Jihun Yun , Jason D. Lee , Kwang-Sung Jun

Direct preference optimization (DPO), a widely adopted offline preference optimization algorithm, aims to align large language models (LLMs) with human-desired behaviors using pairwise preference data. However, the generation of the winning…

Computation and Language · Computer Science 2025-02-19 Yuxin Jiang , Bo Huang , Yufei Wang , Xingshan Zeng , Liangyou Li , Yasheng Wang , Xin Jiang , Lifeng Shang , Ruiming Tang , Wei Wang

Aligning large language models with human preferences has emerged as a critical focus in language modeling research. Yet, integrating preference learning into Text-to-Image (T2I) generative models is still relatively uncharted territory.…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Yi Gu , Zhendong Wang , Yueqin Yin , Yujia Xie , Mingyuan Zhou

Our goal is to enable large language models (LLMs) to balance multiple human preference dimensions; such as helpfulness, safety, and verbosity, through principled and controllable alignment. Existing preference optimization methods,…

Machine Learning · Computer Science 2026-02-03 Mete Erdogan

Offline paired preference optimization algorithms have become a popular approach for fine-tuning on preference data, outperforming traditional supervised fine-tuning in various tasks. However, traditional implementations often involve…

Machine Learning · Computer Science 2024-11-01 Franklin Wang , Sumanth Hegde

With the rapid advancement of large language models (LLMs), aligning policy models with human preferences has become increasingly critical. Direct Preference Optimization (DPO) has emerged as a promising approach for alignment, acting as an…

Artificial Intelligence · Computer Science 2025-07-15 Wenyi Xiao , Zechuan Wang , Leilei Gan , Shuai Zhao , Zongrui Li , Ruirui Lei , Wanggui He , Luu Anh Tuan , Long Chen , Hao Jiang , Zhou Zhao , Fei Wu

The alignment of large language models (LLMs) often assumes that using more clean data yields better outcomes, overlooking the match between model capacity and example difficulty. Challenging this, we propose a new principle: Preference…

Computation and Language · Computer Science 2025-05-15 Chengqian Gao , Haonan Li , Liu Liu , Zeke Xie , Peilin Zhao , Zhiqiang Xu

Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and similar algorithms, reduce the likelihood of harmful…

Recent advances in reinforcement learning for foundation models, such as Group Relative Policy Optimization (GRPO), have significantly improved the performance of foundation models on reasoning tasks. Notably, the advantage function serves…

Artificial Intelligence · Computer Science 2025-09-26 Wenke Huang , Quan Zhang , Yiyang Fang , Jian Liang , Xuankun Rong , Huanjin Yao , Guancheng Wan , Ke Liang , Wenwen He , Mingjun Li , Leszek Rutkowski , Mang Ye , Bo Du , Dacheng Tao

Latent reasoning offers a more efficient alternative to explicit reasoning by compressing intermediate reasoning into continuous representations and substantially shortening reasoning chains. However, existing latent reasoning methods…

Machine Learning · Computer Science 2026-05-01 Jingcheng Deng , Zihao Wei , Liang Pang , Junhong Wu , Shicheng Xu , Zenghao Duan , Huawei Shen

Existing work has shown that o1-level performance can be achieved with limited data distillation, but most existing methods focus on unidirectional supervised fine-tuning (SFT), overlooking the intricate interplay between diverse reasoning…

Machine Learning · Computer Science 2025-09-17 Mengyi Deng , Xin Li , Tingyu Zhu , Zhicheng Yang , Zhijiang Guo , Wei Wang

Aligning text-to-image (T2I) diffusion models with preference optimization is valuable for human-annotated datasets, but the heavy cost of manual data collection limits scalability. Using reward models offers an alternative, however,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Kyungmin Lee , Xiaohang Li , Qifei Wang , Junfeng He , Junjie Ke , Ming-Hsuan Yang , Irfan Essa , Jinwoo Shin , Feng Yang , Yinxiao Li

Direct Preference Optimization (DPO) has emerged as a popular algorithm for aligning pretrained large language models with human preferences, owing to its simplicity and training stability. However, DPO suffers from the recently identified…

Machine Learning · Computer Science 2026-03-20 Haocheng Luo , Zehang Deng , Thanh-Toan Do , Mehrtash Harandi , Dinh Phung , Trung Le